Loading...

Capacity and output power estimation approach of individual behind-the-meter distributed photovoltaic system for demand response baseline estimation

Li, K ; Sharif University of Technology | 2019

647 Viewed
  1. Type of Document: Article
  2. DOI: 10.1016/j.apenergy.2019.113595
  3. Publisher: Elsevier Ltd , 2019
  4. Abstract:
  5. Accurate customer baseline load (CBL) estimation is critical for implementing incentive-based demand response (DR) programs. The increasing penetration of grid-tied distributed photovoltaic systems (DPVS) complicates customers’ load patterns, making the CBL estimation more difficult because the volatile actual load and the intermittent PV output power are coupled together. A PV-load decoupling framework is proposed in this paper to address the above issue. The basic idea is to decouple the actual load power and the PV output power, then estimate them separately. To this end, historical PV output power data of each individual DPVS is required. However, pure historical PV output power data is usually unavailable for small-scale DPVSs, since they are normally located behind the meter, thus only the net load (i.e. actual load power minus PV output power) data is metered. Therefore, this paper proposes a machine learning approach to disaggregate the output power of each individual DPVS from net load data. The proposed approach includes two stages: DPVS capacity estimation and PV output power estimation. The first stage consists of two steps. First, a net load curve optimal pairing-based feature extraction method is proposed to extract features from the discrepancy between two different net load curves of the customers under heterogeneous weather conditions. Second, a multiple support vector regression-based ensemble model with the input features extracted in the first step is established to estimate the DPVS capacity. In the second stage, the output power of each DPVS is estimated by its capacity multiplied by the output power of a standard DPVS. Case studies using a real dataset from Sydney indicate that the proposed approach shows a promising performance on PV output power estimation and can significantly improve the CBL estimation accuracy for customers with DPVSs. © 2019 Elsevier Ltd
  6. Keywords:
  7. Behind-the-meter ; Customer baseline load ; Distributed photovoltaic system ; Extraction ; Feature extraction ; Photovoltaic cells ; Baseline estimation ; Capacity estimation ; Customer baseline loads ; Feature extraction methods ; Incentive-based demand response ; Machine learning approaches ; Photovoltaic systems ; Support vector regression (SVR) ; Sales ; Demand analysis ; Estimation method ; Extraction method ; Photovoltaic system ; Power generation
  8. Source: Applied Energy ; Volume 253 , 2019 ; 03062619 (ISSN)
  9. URL: https://www.sciencedirect.com/science/article/abs/pii/S0306261919312693